Image curves reconstruction by means of robust features

• Grant number: 20/07224-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2020
• End date: September 30, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: João Do Espirito Santo Batista Neto
• Grantee: André Luís Mendes Fakhoury
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 19/07316-0 - Singularity theory and its applications to differential geometry, differential equations and computer vision, AP.TEM

Abstract

One of the current challenges in image processing and computer vision is the mapping of robust characteristics between two- and three-dimensional spaces. This process can be simplified by reducing the amount of information, representing curves from points (called robust characteristics or important points). From robust features, curves can be reconstructed with a minimum error. To that, image contours must be extracted and then analyzed as discrete curves and, thus, reduced to finite important points. This project aims to analyze the extraction of important points from discrete curves computed from real images, followed by a reconstruction process, using polygonal curves. (AU)